INDEX

Explanations

references to specific brands, particularly Jaguar

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 '\''

-0.16

-0.15

unix

-0.15

UIFont

-0.14

acam

-0.14

byter

-0.14

tat

-0.13

UNK

-0.13

elow

-0.13

berries

-0.13

POSITIVE LOGITS

rypton

0.15

acie

0.15

ÑģÐ¸Ð»ÑĮ

0.15

NB

0.14

åī¯

0.14

ullo

0.14

abaj

0.14

ulin

0.13

cury

0.13

SpinBox

0.13

Activations Density 0.001%

references to specific brands, particularly Jaguar

No Comments

No Known Activations